We propose a Day Ahead Market-Intra Day Market (DAM-IDM) forecasting tool that facilitates the participation of PV power into the DAM and IDM and consists of four forecasters. The forecasters have been developed according to operational rules of DAM and IDM. For the implementation of the forecasting tool, we have compared two Deep Learning models, i.e., CNN and Transformer. We emphasize on the development of a simple, low- cost, and highly efficient forecasting methodology that will be attractive for the potential stakeholders.
The forecasting tool has been evaluated on data from five PV plants in Kozani area, Greece (5 csv files PV#1, PV#2, …, PV#5). The historical PV production data cover a period from 01/01/2020 to 10/03/2020 with 15-min resolution.
Citations
If you use our dataset in your research or find our repository useful, please cite our work
D. Kothona, K. Spyropoulos, C. Valelis, C. Koutsis, K. Ch. Chatzisavvas, G. C. Christoforidis,
Deep learning forecasting tool facilitating the participation of photovoltaic systems into day-ahead and intra-day electricity markets,
Sustainable Energy, Grids and Networks,
2023,
101149,
ISSN 2352-4677,
https://doi.org/10.1016/j.segan.2023.101149
License
Uniway Dataset is available under Creative Commons BY-NC-SA 4.0 license
Download
Download the files of PV Power Forecasting (SEGAN, 2023) here